A One-Class-Classifier-Based Negative Data Generation Method for Rapid Earthquake-Induced Landslide Susceptibility Mapping

Machine learning with extensive labelled training samples (e.g., positive and negative data) has been received much attention to address earthquake-induced landslide susceptibility mapping (LSM). However, massive labelled training data required by machine learning, particularly the precise negative data (i.e., non-landslide area), cannot be easily and efficiently collected. To address this issue, this study presents a one class classifier based negative data generation method for rapid earthquake-induced LSM. First, an incomplete landslide inventory (i.e., positive data) was produced with the aid of change detection using before-and-after satellite images and Geographic Information System (GIS). Second, one class classifier was utilized to compute the probability of landslide occurrence based on the incomplete landslide inventory, followed by the negative data generation from the low landslide susceptibility areas. Third, positive data as well as the generated negative data (i.e., non-landslide) were compounded to train traditional binary classifier to produce final LSM. Experimental results suggest that the proposed method is capable to achieve a comparable result with methods using the complete landslide inventory and display a good correspondence with recent landslide events, making it a suitable method for rapid earthquake-induced LSM. The finding in this study would be useful in regional disaster planning and risk reduction.